{
  "lesson": "58-vision-encoder-patches",
  "title": "Vision Encoder Patches",
  "questions": [
    {
      "stage": "pre",
      "question": "Why does a Vision Transformer use patches instead of feeding one pixel per token?",
      "options": [
        "Patches are required by PyTorch",
        "Pixel-per-token sequences explode attention compute quadratically and lose tractability at typical resolutions",
        "Patches improve image quality",
        "It avoids using a tokenizer"
      ],
      "correct": 1,
      "explanation": "A 224x224 image is 150528 pixel tokens. Attention is quadratic in length, so 16x16 patching shrinks the sequence to 196 tokens and makes the model tractable."
    },
    {
      "stage": "pre",
      "question": "What is the relationship between Conv2d with kernel = stride = patch_size and flatten-then-linear?",
      "options": [
        "Conv2d adds non-linearity",
        "They produce different outputs",
        "Conv2d is a faster way to spell the same linear projection over each patch",
        "Flatten-then-linear is impossible"
      ],
      "correct": 2,
      "explanation": "Each Conv2d output location dot-products the patch pixels with one filter, which is identical to flatten-then-linear."
    },
    {
      "stage": "check",
      "question": "Why is the 2D sinusoidal position embedding deterministic instead of learned?",
      "options": [
        "Fixed sin/cos signals interpolate cleanly to grids the model never saw, which is useful when resolution changes",
        "Random init is required",
        "It saves disk space",
        "Learned positions are illegal"
      ],
      "correct": 0,
      "explanation": "Fixed sinusoidal positions are deterministic across resolutions and let the same encoder run on inputs it was not trained on."
    },
    {
      "stage": "check",
      "question": "What is the output sequence length of a 224x224 image with patch_size=16 and one CLS token?",
      "options": [
        "224",
        "256",
        "196",
        "197"
      ],
      "correct": 3,
      "explanation": "224/16 = 14, so 14x14 = 196 patches, plus one CLS token for 197 total tokens."
    },
    {
      "stage": "check",
      "question": "Why is reconstruction (unfold then unflatten) a useful sanity check on the patch front end?",
      "options": [
        "It speeds up inference",
        "Round-tripping pixels through patch-flatten with no projection must equal the input; failure means the unfold math is wrong",
        "It improves accuracy",
        "It is required by ONNX"
      ],
      "correct": 1,
      "explanation": "The patch step is invertible without projection. If the round-trip drifts, the unfold logic is bugged and the rest of the encoder is unsafe."
    },
    {
      "stage": "post",
      "question": "What changes when you swap a learned position embedding for the 2D sinusoidal one in this lesson?",
      "options": [
        "Nothing changes",
        "Sinusoidal positions are random per step",
        "Learned positions can fit a fixed resolution slightly better; sinusoidal positions transfer to new resolutions without retraining",
        "Sinusoidal positions cost more parameters"
      ],
      "correct": 2,
      "explanation": "Learned positions are flexible at one resolution. Sinusoidal positions cost zero parameters and survive resolution shifts."
    }
  ]
}